Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3656 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 21.4099. Min Range: -21.4099
Max Act: 21.4099. Min Act: -0.1700
Data Index: 788169 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 21.4099. Min Range: -21.4099
Max Act: 20.9099. Min Act: -0.1700
Data Index: 8162286 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 21.4099. Min Range: -21.4099
Max Act: 20.5349. Min Act: -0.1700
Data Index: 4860961 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 21.4099. Min Range: -21.4099
Max Act: 20.2849. Min Act: -0.1700
Data Index: 8714658 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 21.4099. Min Range: -21.4099
Max Act: 20.1599. Min Act: -0.1700
Data Index: 2021036 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 21.4099. Min Range: -21.4099
Max Act: 20.1599. Min Act: -0.1700
Data Index: 2266726 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 21.4099. Min Range: -21.4099
Max Act: 20.0349. Min Act: -0.1700
Data Index: 7108453 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 21.4099. Min Range: -21.4099
Max Act: 20.0349. Min Act: -0.1700
Data Index: 5210370 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 21.4099. Min Range: -21.4099
Max Act: 19.9099. Min Act: -0.1700
Data Index: 8193985 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 21.4099. Min Range: -21.4099
Max Act: 19.9099. Min Act: -0.1700
Data Index: 300697 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 21.4099. Min Range: -21.4099
Max Act: 19.9099. Min Act: -0.1700
Data Index: 3840706 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 21.4099. Min Range: -21.4099
Max Act: 19.7849. Min Act: -0.1700
Data Index: 4423791 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 21.4099. Min Range: -21.4099
Max Act: 19.7849. Min Act: -0.1700
Data Index: 6509676 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 21.4099. Min Range: -21.4099
Max Act: 19.7849. Min Act: -0.1700
Data Index: 4537783 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 21.4099. Min Range: -21.4099
Max Act: 19.6599. Min Act: -0.1700
Data Index: 7600276 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 21.4099. Min Range: -21.4099
Max Act: 19.6599. Min Act: -0.1700
Data Index: 7885023 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 21.4099. Min Range: -21.4099
Max Act: 19.6599. Min Act: -0.1700
Data Index: 5074211 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 21.4099. Min Range: -21.4099
Max Act: 19.5349. Min Act: -0.1700
Data Index: 4020854 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 21.4099. Min Range: -21.4099
Max Act: 19.6599. Min Act: -0.1700
Data Index: 4016806 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 21.4099. Min Range: -21.4099
Max Act: 19.5349. Min Act: -0.1700
Data Index: 8190488 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19